<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="martinez-lorenzo-etal-2023-cross">
    <titleInfo>
        <title>Cross-lingual AMR Aligner: Paying Attention to Cross-Attention</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Abelardo</namePart>
        <namePart type="given">Carlos</namePart>
        <namePart type="family">Martínez Lorenzo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pere</namePart>
        <namePart type="given">Lluís</namePart>
        <namePart type="family">Huguet Cabot</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Roberto</namePart>
        <namePart type="family">Navigli</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Rogers</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jordan</namePart>
            <namePart type="family">Boyd-Graber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Naoaki</namePart>
            <namePart type="family">Okazaki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Toronto, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper introduces a novel aligner for Abstract Meaning Representation (AMR) graphs that can scale cross-lingually, and is thus capable of aligning units and spans in sentences of different languages. Our approach leverages modern Transformer-based parsers, which inherently encode alignment information in their cross-attention weights, allowing us to extract this information during parsing. This eliminates the need for English-specific rules or the Expectation Maximization (EM) algorithm that have been used in previous approaches. In addition, we propose a guided supervised method using alignment to further enhance the performance of our aligner. We achieve state-of-the-art results in the benchmarks for AMR alignment and demonstrate our aligner’s ability to obtain them across multiple languages. Our code will be available at [https://www.github.com/babelscape/AMR-alignment](https://www.github.com/babelscape/AMR-alignment).</abstract>
    <identifier type="citekey">martinez-lorenzo-etal-2023-cross</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-acl.109</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-acl.109</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>1726</start>
            <end>1742</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Cross-lingual AMR Aligner: Paying Attention to Cross-Attention
%A Martínez Lorenzo, Abelardo Carlos
%A Huguet Cabot, Pere Lluís
%A Navigli, Roberto
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F martinez-lorenzo-etal-2023-cross
%X This paper introduces a novel aligner for Abstract Meaning Representation (AMR) graphs that can scale cross-lingually, and is thus capable of aligning units and spans in sentences of different languages. Our approach leverages modern Transformer-based parsers, which inherently encode alignment information in their cross-attention weights, allowing us to extract this information during parsing. This eliminates the need for English-specific rules or the Expectation Maximization (EM) algorithm that have been used in previous approaches. In addition, we propose a guided supervised method using alignment to further enhance the performance of our aligner. We achieve state-of-the-art results in the benchmarks for AMR alignment and demonstrate our aligner’s ability to obtain them across multiple languages. Our code will be available at [https://www.github.com/babelscape/AMR-alignment](https://www.github.com/babelscape/AMR-alignment).
%R 10.18653/v1/2023.findings-acl.109
%U https://aclanthology.org/2023.findings-acl.109
%U https://doi.org/10.18653/v1/2023.findings-acl.109
%P 1726-1742

Markdown (Informal)

[Cross-lingual AMR Aligner: Paying Attention to Cross-Attention](https://aclanthology.org/2023.findings-acl.109) (Martínez Lorenzo et al., Findings 2023)

• Cross-lingual AMR Aligner: Paying Attention to Cross-Attention (Martínez Lorenzo et al., Findings 2023)

ACL

• Abelardo Carlos Martínez Lorenzo, Pere Lluís Huguet Cabot, and Roberto Navigli. 2023. Cross-lingual AMR Aligner: Paying Attention to Cross-Attention. In Findings of the Association for Computational Linguistics: ACL 2023, pages 1726–1742, Toronto, Canada. Association for Computational Linguistics.